kw_tools/web/clickbot_100.py

import dataset
from selenium import webdriver
import traceback
import time
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
import pymysql
pymysql.install_as_MySQLdb()


path = 'C:\portable\chromedriver'
path_z = '/Users/zooeytsai/Downloads/chromedriver 4'
def restart_browser():
    options = webdriver.ChromeOptions()
    # options.add_argument("user-agent=%s" % rua())
    options.add_argument('--headless')
    driver=webdriver.Chrome(options=options,executable_path=path_z)
    driver.set_window_size(950, 20000)
    return driver


def process_one(kw,domain):
    # db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
    db_local = dataset.connect('mysql://root:jondae350@localhost/ig_tags')
    table=db_local['google_rank']

    driver=restart_browser()
    # escaped_search_term=urllib.parse.quote(term)
    googleurl = 'https://www.google.com/?num=100'
    driver.get(googleurl)
    time.sleep(6)
    send_kw_elmt = driver.find_element(By.XPATH,'/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')
    send_kw_elmt.send_keys(kw)
    time.sleep(3)
    send_kw_elmt.send_keys(Keys.ENTER)
    time.sleep(6)
    elmts=driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")

    cnt=1
    datadict={'搜尋詞':[],'結果標題':[],'結果網址':[],'結果名次':[]}
    
    for elmt in elmts:
        try:
            href=elmt.get_attribute('href')
            if domain in href:
                datadict['搜尋詞'].append(kw)
                datadict['結果標題'].append(elmt.text)
                datadict['結果網址'].append(href)
                datadict['結果名次'].append(str(cnt))
            cnt+=1
        except:
            print('href2 exception')
            traceback.print_exc()
    
    driver.quit()
    time.sleep(60)
    # db.close()
    db_local.close()
    return datadict